Intrusion Detection in Software Defined Networks with Self-organized Maps

The Software Defined Network (SDN) architecture provides new opportunities to implement security mechanisms in terms of unauthorized activities detection. At the same time, there are certain risks associated with this technology. The presented approach covers a conception of the measurement method, virtual testbed and classification mechanism for SDNs. The paper presents a measurement method which allows collecting network traffic flow parameters, generated by a virtual SDN environment. The collected dataset can be used in machine learning methods to detect unauthorized activities. Keywords—IDS dataset, machine learning, metasploit, network security, network simulation, open flow, virtualization.